INDEX

Explanations

references to corporate entities and their business activities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

intl

-0.14

ãĤ¦ãĥĪ

-0.14

heck

-0.14

 Banner

-0.13

leaning

-0.13

ÃŃc

-0.13

ë¬

-0.13

ä»®

-0.13

hal

-0.13

achi

-0.13

POSITIVE LOGITS

 previously

0.23

 last

0.20

 earlier

0.20

 hope

0.19

 Previously

0.18

 recently

0.18

 already

0.16

Previously

0.16

Earlier

0.16

 also

0.16

Activations Density 0.100%

references to corporate entities and their business activities

No Comments

No Known Activations